cs.CL（2025-03-12）

📊 共 30 篇论文 | 🔗 4 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (23 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (7 🔗2)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (23 篇)

#题目一句话要点标签🔗⭐
1 Review GIDE -- Restaurant Review Gastrointestinal Illness Detection and Extraction with Large Language Models 利用大型语言模型进行餐厅评论中胃肠道疾病的检测与信息抽取 large language model
2 A Survey on Enhancing Causal Reasoning Ability of Large Language Models 综述：提升大型语言模型因果推理能力的研究进展 large language model
3 What's In Your Field? Mapping Scientific Research with Knowledge Graphs and Large Language Models 提出基于知识图谱和大语言模型的科学研究映射方法 large language model ✅
4 TRACE: Real-Time Multimodal Common Ground Tracking in Situated Collaborative Dialogues TRACE：用于情境化协作对话的实时多模态共同基础追踪系统 multimodal
5 Rethinking Prompt-based Debiasing in Large Language Models 揭示大语言模型中基于Prompt的去偏见方法的局限性与虚假繁荣 large language model
6 Harmonizing Large Language Models with Collaborative Behavioral Signals for Conversational Recommendation 提出融合协同行为信号的大语言模型对话推荐框架，提升推荐相关性。 large language model
7 Medical Large Language Model Benchmarks Should Prioritize Construct Validity 医学大语言模型评测应优先考虑建构效度，避免唯榜单论 large language model
8 Battling Misinformation: An Empirical Study on Adversarial Factuality in Open-Source Large Language Models 研究表明，开源大语言模型在对抗性事实性攻击下的鲁棒性差异显著 large language model
9 Probabilistic Reasoning with LLMs for k-anonymity Estimation 提出BRANCH方法，利用LLM进行概率推理，提升k-匿名性估计的准确率。 large language model chain-of-thought
10 Attention Reveals More Than Tokens: Training-Free Long-Context Reasoning with Attention-guided Retrieval 提出Attrieval：利用注意力引导检索，实现无需训练的长文本推理 large language model chain-of-thought
11 MOAT: Evaluating LMMs for Capability Integration and Instruction Grounding 提出MOAT基准，评估LMMs在能力集成和指令理解方面的性能 multimodal ✅
12 Reassessing Active Learning Adoption in Contemporary NLP: A Community Survey 通过社区调查重新评估主动学习在现代NLP中的应用现状与挑战 large language model
13 Cost-Optimal Grouped-Query Attention for Long-Context Modeling 提出面向长文本建模的成本优化分组查询注意力机制，显著降低计算成本。 large language model
14 Generative AI for Named Entity Recognition in Low-Resource Language Nepali 探索生成式AI在低资源尼泊尔语命名实体识别中的应用 large language model
15 How to Protect Yourself from 5G Radiation? Investigating LLM Responses to Implicit Misinformation 提出EchoMist基准测试，评估并提升LLM对隐性错误信息的防御能力 large language model
16 Safer or Luckier? LLMs as Safety Evaluators Are Not Robust to Artifacts 揭示LLM安全评估器对输入伪影的脆弱性，提出陪审团评估方法以提升鲁棒性。 large language model
17 MoC: Mixtures of Text Chunking Learners for Retrieval-Augmented Generation System 提出MoC框架，优化RAG系统中文本分块策略，提升检索增强生成效果 large language model
18 Plan-and-Act: Improving Planning of Agents for Long-Horizon Tasks 提出Plan-and-Act框架，提升LLM智能体在长程任务中的规划能力 large language model
19 Token Weighting for Long-Range Language Modeling 提出基于token权重调整的训练方法，提升LLM在长文本建模任务中的性能。 large language model
20 VaxGuard: A Multi-Generator, Multi-Type, and Multi-Role Dataset for Detecting LLM-Generated Vaccine Misinformation VaxGuard：多生成器、多类型、多角色的疫苗虚假信息检测数据集 large language model
21 HaploVL: A Single-Transformer Baseline for Multi-Modal Understanding HaploVL：单Transformer架构的多模态理解基线模型 large language model
22 Leveraging Retrieval Augmented Generative LLMs For Automated Metadata Description Generation to Enhance Data Catalogs 利用检索增强生成式LLM自动生成元数据描述，提升数据目录质量。 large language model
23 Learning to Contextualize Web Pages for Enhanced Decision Making by LLM Agents 提出LCoW框架，通过上下文理解增强LLM Agent在Web任务中的决策能力 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (7 篇)

#题目一句话要点标签🔗⭐
24 Quality Over Quantity? LLM-Based Curation for a Data-Efficient Audio-Video Foundation Model AVVA：基于LLM的数据筛选框架，提升音视频基础模型的数据效率 contrastive learning large language model foundation model
25 xVLM2Vec: Adapting LVLM-based embedding models to multilinguality using Self-Knowledge Distillation 提出xVLM2Vec，利用自知识蒸馏提升LVLM在多语言多模态嵌入任务上的性能。 distillation large language model multimodal
26 DAST: Difficulty-Aware Self-Training on Large Language Models DAST：一种难度感知的大语言模型自训练框架，提升难题解决能力 DPO large language model
27 Aligning to What? Limits to RLHF Based Alignment 研究表明基于人类反馈的强化学习（RLHF）在消除LLM偏见方面存在局限性 reinforcement learning RLHF DPO
28 Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning Search-R1：利用强化学习训练LLM进行推理并有效利用搜索引擎 reinforcement learning large language model ✅
29 BAMBI: Developing Baby Language Models for Italian BAMBI：为意大利语开发模拟儿童语言习得的Baby语言模型 curriculum learning large language model multimodal
30 Domain Adaptation for Japanese Sentence Embeddings with Contrastive Learning based on Synthetic Sentence Generation 提出SDJC，利用对比学习和合成数据进行日语句子嵌入的领域自适应 contrastive learning ✅

⬅️ 返回 cs.CL 首页 · 🏠 返回主页